© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 23786
    Prev
    Next
    INDEX
    Explanations

    instances of the word "One" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "One" used to introduce statements or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.82
    osponsors
    -0.80
    ÃįÃį
    -0.78
    lems
    -0.73
    eworld
    -0.71
     actionGroup
    -0.71
    jong
    -0.70
    ivas
    -0.69
    axy
    -0.67
    emies
    -0.67
    POSITIVE LOGITS
     thing
    1.15
     hundred
    1.09
     reason
    1.08
     caveat
    1.07
     drawback
    1.06
     wonders
    1.04
     downside
    0.98
     aspect
    0.96
     pecul
    0.96
     notable
    0.95
    Activations Density 0.087%

    No Known Activations